Scientific direction Development of key enabling technologies
Transfer of knowledge to industry

PostDocs : selection by topics

Technological challenges >> Artificial intelligence & Data intelligence
6 proposition(s).

See all positions

Hybrid CMOS / spintronic circuits for Ising machines

Département Composants Silicium (LETI)

Laboratoire Dispositifs Quantiques et Connectivité

01-01-2021

PsD-DRT-21-0025

louis.hutin@cea.fr

The proposed research project is related to the search for hardware accelerators for solving NP-hard optimization problems. Such problems, for which finding exact solutions in polynomial time is out of reach for deterministic Turing machines, find many applications in diverse fields such as logistic operations, circuit design, medical diagnosis, Smart Grid management etc. One approach in particular is derived from the Ising model, and is based on the evolution (and convergence) of a set of binary states within an artificial neural network (ANN).In order to improve the convergence speed and accuracy, the network elements may benefit from an intrinsic and adjustable source of fluctuations. Recent proof-of-concept work highlights the interest of implementing such neurons with stochastic magnetic tunnel junctions (MTJ). The main goals will be the simulation, dimensioning and fabrication of hybrid CMOS/MTJ elements. The test vehicles will then be characterized in order to validate their functionality. This work will be carried out in the frame of a scientific collaboration between CEA-Leti and Spintec.

Download the offer (.zip)

Combinatorial optimization of base materials for the design of new materials

Département Métrologie Instrumentation et Information (LIST)

Laboratoire Intelligence Artificielle et Apprentissage Automatique

01-02-2021

PsD-DRT-21-0057

jean-philippe.poli@cea.fr

The design of new materials is a field of growing interest, especially with the emergence of additive manufacturing processes, thin film deposition, etc. In order to create new materials to target properties of interest for an application area, it is often necessary to mix several raw materials. A physicochemical modeling of the reactions that occur during this mixing is often very difficult to obtain, especially when the number of raw materials increases. We want to free ourselves as much as possible from this modeling. From experimental data and business knowledge, the goal of this project is to create a symbolic AI capable of groping for the optimal mixture to achieve one or more given properties. The idea is to adapt existing methods of operations research, such as combinatorial optimization, in a context of imprecise knowledge. We will focus on different use cases such as electric batteries, solvents for photovoltaic cells and anti-corrosion materials. Within the project, you will: ? Study the state of the art, ? Propose one or several algorithms to prototype, and their evaluation, ? Disseminate the resulting innovations to the consortium and the scientific community, through presentations, contributions to technical reports and / or scientific publications. Maximum duration: 18-24 months (regarding your experience).

Download the offer (.zip)

Application of a MDE approach to AI-based planning for robotic and autonomous systems

Département Ingénierie Logiciels et Systèmes (LIST)

Labo.conception des systèmes embarqués et autonomes

01-05-2020

PsD-DRT-20-0063

matteo.morelli@cea.fr

The complexity of robotics and autonomous systems (RAS) can only be managed with well-designed software architectures and integrated tool chains that support the entire development process. Model-driven engineering (MDE) is an approach that allows RAS developers to shift their focus from implementation to the domain knowledge space and to promote efficiency, flexibility and separation of concerns for different development stakeholders. One key goal of MDE approaches is to be integrated with available development infrastructures from the RAS community, such as ROS middleware, ROSPlan for task planning, BehaviorTree.CPP for execution and monitoring of robotics tasks and Gazebo for simulation. The goal of this post-doc is to investigate and develop modular, compositional and predictable software architectures and interoperable design tools based on models, rather than code-centric approaches. The work must be performed in the context of European projects such as RobMoSys (www.robmosys.eu), and other initiatives on AI-based task planning and task execution for robotics and autonomous systems. The main industrial goal is to simplify the effort of RAS engineers and thus allowing the development of more advanced, more complex autonomous systems at an affordable cost. In order to do so, the postdoctoral fellow will contribute to set-up and consolidate a vibrant ecosystem, tool-chain and community that will provide and integrate model-based design, planning and simulation, safety assessment and formal validation and verification capabilities.

Download the offer (.zip)

Development of decentralized and resilient algorithms for federated learning

Département Métrologie Instrumentation et Information (LIST)

Laboratoire Intelligence Artificielle et Apprentissage Automatique

01-09-2021

PsD-DRT-21-0091

meritxell.vinyals@cea.fr

The postdoctoral fellow will join the FANTASTYC project (internal to CEA) which puts together researchers on distributed ledger technology, privacy and machine learning with the aim of developing software assets for decentralized, privacy-preserving and resilient federated learning. In more detail, the first objective of this fellowship is to envisage a fully decentralized efficient version of the federated learning, replacing communication with the server by peer-to-peer communication between individual clients on some communication graph. On doing that, the postdoctoral fellow is expected to tackle some of the open challenges involved by passing to decentralized learning, including: (1) the design, specification and implementation of resource-aware decentralised learning protocols; and (2) tackling the compromise between generic and personalized models depending on the evaluated non-IID data distributions available to individual clients (e.g. different models for clusters of participants). The other focus of this position will be the study of the robustness of distributed federated learning against the presence of malicious participants (i.e. Byzantine attacks)

Download the offer (.zip)

Post-doctoral position in AI safety and assurance at CEA LIST

Département Ingénierie Logiciels et Systèmes (LIST)

Labo.conception des systèmes embarqués et autonomes

01-10-2020

PsD-DRT-20-0110

morayo.adedjouma@cea.fr

The position is related to safety assessment and assurance of AI (Artificial Intelligence)-based systems that used machine-learning components during operation time for performing autonomy functions. Currently, for non-AI system, the safety is assessed prior to the system deployment and the safety assessment results are compiled into a safety case that remains valid through system life. For novel systems integrating AI components, particularly the self-learners systems, such engineering and assurance approach are not applicable as the system can exhibit new behavior in front of unknown situations during operation. The goal of the postdoc will be to define an engineering approach to perform accurate safety assessment of AI systems. A second objective is to define assurance case artefacts (claims, evidences, etc.) to obtain & preserve justified confidence in the safety of the system through its lifetime, particularly for AI system with operational learning. The approach will be implemented in an open-source framework that it will be evaluated on industry-relevant applications. The position holder will join a research and development team in a highly stimulating environment with unique opportunities to develop a strong technical and research portfolio. He will be required to collaborate with LSEA academic & industry partners, to contribute and manage national & EU projects, to prepare and submit scientific material for publication, to provide guidance to PhD students.

Download the offer (.zip)

Machine learning technics and knowledge-based simulator combined for dynamic process state estimation

Département Métrologie Instrumentation et Information (LIST)

Laboratoire Science des Données et de la Décision

01-11-2021

PsD-DRT-21-0120

laurence.cornez@cea.fr

This project aims to estimate the real state of a dynamic process for liquid-liquid extraction through the real data record. Data of this kind are uncertain due to exogenous variables. They are not included inside the simulator PAREX+ dedicated to the dynamic process. So, the first part of the project is to collect data from simulator. By this way the operational domain should be well covered and the dynamic response recorded. Then, the project focuses to solve the inverse problem by using convolutionnal neural networks on times series. Maybe a data enrichment could be necessary to perfect zones and improve estimations. Finally, the CNN will be tested on real data and integrate the uncertainty inside its estimations. At the end, the model built needs to be used in operational conditions to help diagnosis and improve the real-time control to ensure that the dynamic observed is the one needed.

Download the offer (.zip)

See all positions